Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2922 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.1690. Min Range: -3.1690

Max Act: 3.1690. Min Act: -0.1700

Data Index: 6306996 (Open Web Text)

Max Activating Token Index: 422

Text #1

Max Range: 3.1690. Min Range: -3.1690

Max Act: 3.0004. Min Act: -0.1700

Data Index: 5240733 (Open Web Text)

Max Activating Token Index: 643

Text #2

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.9346. Min Act: -0.1700

Data Index: 7548445 (Open Web Text)

Max Activating Token Index: 222

Text #3

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.9463. Min Act: -0.1700

Data Index: 3129046 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.9062. Min Act: -0.1700

Data Index: 5671297 (Open Web Text)

Max Activating Token Index: 801

Text #5

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.9342. Min Act: -0.1700

Data Index: 451051 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.9306. Min Act: -0.1700

Data Index: 1081082 (Open Web Text)

Max Activating Token Index: 112

Text #7

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8889. Min Act: -0.1700

Data Index: 2998756 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.9170. Min Act: -0.1700

Data Index: 4769587 (Open Web Text)

Max Activating Token Index: 503

Text #9

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8339. Min Act: -0.1700

Data Index: 3867783 (Open Web Text)

Max Activating Token Index: 800

Text #10

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8885. Min Act: -0.1700

Data Index: 6394348 (Open Web Text)

Max Activating Token Index: 252

Text #11

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8473. Min Act: -0.1700

Data Index: 4455076 (Open Web Text)

Max Activating Token Index: 410

Text #12

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8715. Min Act: -0.1700

Data Index: 2749963 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8606. Min Act: -0.1700

Data Index: 2373156 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8562. Min Act: -0.1700

Data Index: 2305385 (Open Web Text)

Max Activating Token Index: 212

Text #15

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8327. Min Act: -0.1700

Data Index: 8516438 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8535. Min Act: -0.1700

Data Index: 6144713 (Open Web Text)

Max Activating Token Index: 319

Text #17

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8258. Min Act: -0.1700

Data Index: 8825766 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.8652. Min Act: -0.1700

Data Index: 3484977 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 3.1690. Min Range: -3.1690

Max Act: 2.7932. Min Act: -0.1700

Data Index: 6258539 (Open Web Text)

Max Activating Token Index: 395